The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts to perform data processing, validation, and report generation. The scripts/product_profile.py entry point invokes the CLI in scripts/copycat_product_profile/cli.py to handle init, validate, and portfolio commands. These scripts operate on local JSON files within the workspace and do not invoke arbitrary shell commands or external binaries.
[DATA_PROCESSING]: The logic in scripts/copycat_product_profile/profile.py involves parsing JSON data, validating it against a schema, and writing formatted Markdown tables. It uses an atomic write pattern with tempfile.NamedTemporaryFile to ensure data integrity during file operations.
[NO_CODE_INJECTION]: The skill uses static templates for Markdown generation and performs standard dictionary lookups for JSON data. No dynamic code evaluation (e.g., eval, exec) or unsafe deserialization (e.g., pickle) was detected.
[SAFE_PRACTICES]: The skill follows best practices for market research agents by instructing the agent to resolve official domains using developer metadata and to verify claims using multiple evidence classes (e.g., official_claim, user_validated).

copycat-market-research